RGB

class torchvision.transforms.v2.RGB

Convert images or videos to RGB (if they are already not RGB).

If the input is a torch.Tensor, it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions

transform(inpt: Any, params: dict[str, Any]) → Any

Method to override for custom transforms.

See How to write your own v2 transforms